Loading the SOTA2 catalog…
SOTA2 Research · benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
| Task | Dataset | Domain | Trend | Results | Last Update |
|---|---|---|---|---|---|
| Class-incremental learning | CIFAR-100 10 (test) | 105 | Mar 16, 2026 | ||
| Link Prediction | ogbl-collab (test) | 105 | May 28, 2026 | ||
| Scene Text Spotting | Total-Text (test) |
| 105 |
| Feb 26, 2026 |
| Stereo Matching | KITTI 2012 (test) | 105 | May 12, 2026 |
|---|
| Temporal Action Segmentation | GTEA | 105 | Apr 3, 2026 |
|---|
| Video Generation | UCF-101 (test) | 105 | Jun 17, 2026 |
|---|
| Image Classification | MNIST rotated (test) | 105 | Feb 26, 2026 |
|---|
| Sentiment Classification | Stanford Sentiment Treebank SST-2 (test) | 105 | Apr 21, 2026 |
|---|
| Long sequence classification | LRA (Long Range Arena) (test) | 105 | Jun 29, 2026 |
|---|
| Fine-grained Classification | Aircraft | 105 | Jun 29, 2026 |
|---|
| Visual SLAM | TartanAir | 104 | Jul 8, 2026 |
|---|
| Time-series Forecasting | COVID-19 20 regions | 104 | Jun 12, 2026 |
|---|
| ECG Segmentation | ISP (test) | 104 | May 18, 2026 |
|---|
| Offline Reinforcement Learning under Gravity Shift | MuJoCo Ant | 104 | May 26, 2026 |
|---|
| Offline Reinforcement Learning under Gravity Shift | MuJoCo Hopper | 104 | May 26, 2026 |
|---|
| Offline Reinforcement Learning under Gravity Shift | MuJoCo HalfCheetah | 104 | May 26, 2026 |
|---|
| Modulation Classification | RML 2018.01a | 104 | Apr 14, 2026 |
|---|
| Mathematical Reasoning | MATH 500 | 104 | Jun 24, 2026 |
|---|
| Image Classification | Waterbirds severe in-distribution context (test) | 104 | Apr 3, 2026 |
|---|
| Image Classification | Waterbirds In-context training (test) | 104 | Apr 3, 2026 |
|---|
| Image Classification | iNaturalist OOD (test) | 104 | Apr 3, 2026 |
|---|
| Mathematical Reasoning | AMC 2023 | 104 | Jun 24, 2026 |
|---|
| Hallucination Detection | BioASQ | 104 | May 28, 2026 |
|---|
| Mathematical Reasoning | MATH500 | 104 | Jun 19, 2026 |
|---|
| Job Shop Scheduling Problem | DMU benchmark of JSSP | 104 | May 19, 2026 |
|---|